Research article Energy consumption of on-device machine learning models for IoT intrusion detection

Article Computer Science, Software Engineering

Towards a sustainable artificial intelligence: A case study of energy efficiency in decision tree algorithms

Mariza Ferro et al.

Summary: This study evaluates the energy efficiency of machine learning algorithms and identifies energy-consuming hotspots, aiming to find greener strategies for artificial intelligence.

CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE (2023)

Add to Collection

Proceedings Paper Computer Science, Information Systems

A First Look at Code Obfuscation forWebAssembly

Shrenik Bhansali et al.

Summary: WebAssembly (Wasm) has gained attention as a new standard for performance-oriented web development and is used in various domains beyond web applications. However, with the rise of Wasm-based cryptojacking malware, researching code obfuscation techniques for Wasm programs becomes crucial.

PROCEEDINGS OF THE 15TH ACM CONFERENCE ON SECURITY AND PRIVACY IN WIRELESS AND MOBILE NETWORKS (WISEC '22) (2022)

Add to Collection

Article Computer Science, Information Systems

Evaluating computing performance of deep neural network models with different backbones on IoT-based edge and cloud platforms

Xiaoxuan Wang et al.

Summary: This paper evaluates and predicts the computing performance of different architectures of DNN models in cross-platform and cross-inference frameworks, aiming to improve the deployment and application of resource-constrained DNN models on heterogeneous high-performance computing platforms.

INTERNET OF THINGS (2022)

Add to Collection

Article Computer Science, Information Systems

A Two-layer Fog-Cloud Intrusion Detection Model for IoT Networks

Souradip Roy et al.

Summary: In this paper, the authors investigate intrusion detection techniques for IoT networks and propose a machine learning-based two-layer hierarchical intrusion detection mechanism. The proposed approach outperforms existing methods in terms of accuracy and performance, and offers advantages in improving service time, reducing delay, and optimizing energy utilization.

INTERNET OF THINGS (2022)

Add to Collection

Review Computer Science, Information Systems

Intrusion detection based on Machine Learning techniques in computer networks

Ayesha S. Dina et al.

Summary: Intrusions in computer networks have been on the rise in the past decade, leading researchers to propose signature-based and anomaly-based intrusion detection methods, with Machine Learning techniques playing a key role. This paper provides a comprehensive critical survey of ML-based intrusion detection approaches in the literature over the last ten years, highlighting some open issues for future research.

INTERNET OF THINGS (2021)

Add to Collection

Review Computer Science, Information Systems

Machine learning approaches to IoT security: A systematic literature review

Rasheed Ahmad et al.

Summary: As IoT applications continue to expand, attacks on them are growing rapidly, with recent research trends emphasizing the development of models that integrate big data and machine learning technologies for better security.

INTERNET OF THINGS (2021)

Add to Collection

Article Computer Science, Information Systems

TinyML Meets IoT: A Comprehensive Survey

Lachit Dutta et al.

Summary: The concept of TinyML, involving the implementation of machine learning algorithms within IoT devices, offers advantages such as low latency, effective bandwidth utilization, enhanced data security, privacy, and cost reduction. It enables IoT devices to function reliably without continuous access to cloud services, providing on-premise analytics in settings with inadequate connectivity.

INTERNET OF THINGS (2021)

Add to Collection

Article Computer Science, Information Systems

A Survey of On-Device Machine Learning: An Algorithms and Learning Theory Perspective

Sauptik Dhar et al.

Summary: The predominant paradigm for using machine learning models on a device is to train a model in the cloud and perform inference using the trained model on the device. However, with increased interest in on-device learning, there is a need for a comprehensive survey from a device-agnostic perspective to understand the state of the art and future research directions. This survey reformulates the problem of on-device learning as resource constrained learning, allowing for a fair comparison of tools, techniques, and algorithms from various research areas.

ACM TRANSACTIONS ON INTERNET OF THINGS (2021)

Add to Collection

Article Engineering, Electrical & Electronic

Node-Level Error Control Strategies for Prolonging the Lifetime of Wireless Sensor Networks

Nazli Tekin et al.

Summary: This study proposes a node-level error control strategy for Wireless Sensor Networks using mixed-integer programming to determine the optimum error control method for each sensor node, aiming to maximize network lifetime and meet reliability requirements. The performance evaluations show that the node-level strategy provides significantly prolonged lifetimes and better energy-efficiency compared to network-level strategies, with developed meta-heuristic approaches reducing solution time and approaching optimal solutions.

IEEE SENSORS JOURNAL (2021)

Add to Collection

Article Computer Science, Information Systems

A Survey on Sensor-Based Threats and Attacks to Smart Devices and Applications

Amit Kumar Sikder et al.

Summary: The increasing popularity of smart devices has raised concerns over security threats, particularly attacks that abuse sensors on these devices. Due to the lack of proper security mechanisms, smart devices are vulnerable to sensor-based attacks which can compromise device security and privacy.

IEEE COMMUNICATIONS SURVEYS AND TUTORIALS (2021)

Add to Collection

Article Telecommunications